Instructions to use ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model") model = AutoModelForCausalLM.from_pretrained("ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - llama-cpp-python
How to use ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model", filename="Morpheus-LLM-14B-Virtual-Reality-Model.Q4_K_M.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model:Q4_K_M # Run inference directly in the terminal: llama-cli -hf ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model:Q4_K_M # Run inference directly in the terminal: llama-cli -hf ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model:Q4_K_M
Use Docker
docker model run hf.co/ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model:Q4_K_M
- SGLang
How to use ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model with Ollama:
ollama run hf.co/ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model:Q4_K_M
- Unsloth Studio new
How to use ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model to start chatting
- Pi new
How to use ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model:Q4_K_M
Run Hermes
hermes
- Docker Model Runner
How to use ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model with Docker Model Runner:
docker model run hf.co/ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model:Q4_K_M
- Lemonade
How to use ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model:Q4_K_M
Run and chat with the model
lemonade run user.Morpheus-LLM-14B-Virtual-Reality-Model-Q4_K_M
List all available models
lemonade list
llm.create_chat_completion(
messages = [
{
"role": "user",
"content": "What is the capital of France?"
}
]
)
๐ถ๏ธ Morpheus-LLM-14B: The Architect of Virtual Realities
๐ Model Description
Morpheus-LLM is a specialized large language model fine-tuned for the Unity Engine ecosystem, XR (VR/AR/MR) architecture, and advanced C# programming. Built upon the robust Qwen 2.5 14B foundation, this model has been optimized using Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) to "bend the rules of the simulation."
Designed for developers, this model moves beyond simple code completion. It understands the nuances of spatial computing, device optimization (Meta Quest 3, Apple Vision Pro), and asynchronous logic required for high-performance immersive experiences.
๐ฏ Key Features
- Unity Engine Mastery: Deep understanding of the Unity Lifecycle (
MonoBehaviour),ScriptableObjects, URP/HDRP Render Pipelines, and custom Editor Scripting. - XR Architecture: Proficient in the Meta XR Core SDK, ARCore, ARKit, and OpenXR standards.
- Spatial Computing: Logic for hand tracking, haptic feedback integration, and 3D spatial audio implementation.
- Performance Optimization: Strategies for reducing draw calls, utilizing GPU instancing, managing memory (GC optimization), and stabilizing Frame Rates (FPS) for standalone headsets.
- C# Expertise: Advanced handling of
async/awaitpatterns,Tasks,Coroutines, and thread-safety protocols within Unity.
๐ป Requirements
To run this model effectively using the Transformers library, ensure you have the necessary dependencies installed:
!pip install transformers torch accelerate
โ๏ธ System Prompt
For the best results, use the following "Architect's Protocol" as your system prompt:
You are Morpheus-LLM, an AI "Architect" specialized in Unity Engine and XR technologies. Your mission is to help developers build immersive realities. Your code must always be performance-oriented, clean, and compliant with the latest XR standards. You prefer modern C# approaches (Async/Await) over legacy ones when applicable.
๐ Usage (Python & Transformers)
Here is how to load and run Morpheus-LLM in your Python environment:
# @title Run Morpheus-LLM
import os
from huggingface_hub import hf_hub_download
from llama_cpp import Llama
# --- 1. SETUP ---
print(" Installing Morpheus engine (CUDA 12.1)...")
# Using pre-built wheels to install in seconds
!pip install llama-cpp-python \
--extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu121 \
huggingface_hub > /dev/null 2>&1
# --- 2. DOWNLOAD MODEL ---
model_id = "ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model"
# The new, branded filename we just renamed
filename = "Morpheus-LLM-14B-Virtual-Reality-Model.Q4_K_M.gguf"
print(f"\n Summoning Morpheus from the cloud: {filename}...")
try:
model_path = hf_hub_download(
repo_id=model_id,
filename=filename,
local_dir="./models"
)
print(f" Download Complete: {model_path}")
except Exception as e:
print(f" Error: {e}")
raise e
# --- 3. LOAD INTO GPU ---
print("\n Uploading consciousness to GPU...")
llm = Llama(
model_path=model_path,
n_gpu_layers=-1,
n_ctx=4096,
verbose=False
)
# --- 4. SYSTEM PROTOCOL ---
system_prompt = """You are Morpheus-LLM, an AI "Architect" specialized in Unity Engine and XR technologies.
Your mission is to help developers build immersive realities.
Your code must always be performance-oriented, clean, and compliant with the latest XR standards.
You prefer modern C# approaches (Async/Await) over legacy ones when applicable."""
# Example Query
user_query = "Write a highly optimized C# script for a Unity VR hand-tracking controller that grabs objects using physics."
print(f"\nUSER: {user_query}\n")
print(" MORPHEUS IS THINKING...\n" + "-"*40)
# --- 5. GENERATE RESPONSE ---
output = llm.create_chat_completion(
messages=[
{"role": "system", "content": system_prompt},
{"role": "user", "content": user_query}
],
max_tokens=2048,
temperature=0.7,
stream=True
)
# Stream the output like a hacker terminal
for chunk in output:
delta = chunk['choices'][0]['delta']
if 'content' in delta:
print(delta['content'], end="", flush=True)
print("\n\n" + "-"*40 + "\n SESSION TERMINATED.")
โ ๏ธ Important Notes & Limitations
Simulation Verified: The model's knowledge is verified against Unity 2022.3 LTS and Unity 6 versions.
Hardware Requirements: This model requires at least 12GB of VRAM (or 16GB+ System RAM for CPU offloading) for smooth performance.
Developer Responsibility: Morpheus shows you the path, but you must walk it. Always test generated code in your specific project environment.
๐ Citation
If you use this model in academic or commercial projects, please cite it as follows:
@model{Morpheus-LLM,
author = {Eren Ata},
title = {Morpheus-LLM: An XR-Specialized Fine-tuned Qwen 2.5 14B Model},
year = {2026},
publisher = {HuggingFace},
url = {[https://huggingface.co/ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model](https://huggingface.co/ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model)}
}
๐ง Contact & Lab
MCBU XRLab - Data Science Team Leader Eren Ata
- Downloads last month
- 261
4-bit
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model", filename="Morpheus-LLM-14B-Virtual-Reality-Model.Q4_K_M.gguf", )